Hacker News: blinkbat

New comment by blinkbat in "Talk Without Talking"

blinkbat — Fri, 30 Oct 2026 20:53:35 +0000

Faq doesn't seem to indicate whether it works or not

New comment by blinkbat in "Sleep framework: A new way for LLMs to retain knowledge in continual learning"

blinkbat — Fri, 30 Oct 2026 20:43:31 +0000

Does this shit actually work lol

New comment by blinkbat in "Poll: How do you run your coding agents day to day?"

blinkbat — Fri, 30 Oct 2026 15:52:51 +0000

several sessions in one or multiple instances of vscode.

New comment by blinkbat in "HN: Storm – We killed the job interview. Candidates just do the job now"

blinkbat — Tue, 27 Oct 2026 15:06:04 +0000

Terrible slop copy.

New comment by blinkbat in "What are you using for agentic coding now?"

blinkbat — Tue, 27 Oct 2026 04:33:50 +0000

LLMs

New comment by blinkbat in "Ask HN: Can superintelligent AI alignement be decentralized?"

blinkbat — Sun, 25 Oct 2026 18:06:26 +0000

Bit vague innit

New comment by blinkbat in "The Art of Unix Programming"

blinkbat — Sat, 24 Oct 2026 17:58:16 +0000

The art of https

New comment by blinkbat in "Tell HN: The Amount of Irrelevant Content on Here Is Insane"

blinkbat — Fri, 23 Oct 2026 21:16:23 +0000

Lol

New comment by blinkbat in "Ask HN: Time to read those programming books?"

blinkbat — Thu, 22 Oct 2026 18:54:55 +0000

Writing is the slowest part

New comment by blinkbat in "Hello World, AI Doompop"

blinkbat — Wed, 21 Oct 2026 14:42:22 +0000

at the risk of sounding dismissive, fuck this lame shit

New comment by blinkbat in "Ask HN: Are agent benchmarks the new credit ratings?"

blinkbat — Tue, 20 Oct 2026 20:14:08 +0000

Tests and community are far better indicators

New comment by blinkbat in "Ask HN: Time to read those programming books?"

blinkbat — Tue, 20 Oct 2026 19:51:03 +0000

yes, you get better _at programming_, specifically your own programs, and in a general sense. but is there a way to hone the reading of code that is not yours?

> Now we are using LLMs to write the code to the point where we need to assign ourselves homework to keep our skills?

yes!

> Why not just use the LLM in a way that doesn't prevent us from absorbing the knowledge?

the economic viability of this is unproven in our new future.

Ask HN: Time to read those programming books?

blinkbat — Tue, 20 Oct 2026 17:53:36 +0000

As llm usage becomes the way we all program and reading code becomes more valuable than writing it, what programming books would you recommend to boost this particular skill?

Comments URL: https://news.ycombinator.com/item?id=50170094

Points: 6

# Comments: 13

New comment by blinkbat in "Ask HN: Is Agentic Coding really faster?"

blinkbat — Sun, 18 Oct 2026 22:46:46 +0000

typing speed was never my strong suit, I also was heavily into readable formatting which I often did by hand in a mixed team. so I'm not one of these stays-in-vim people that can pop out reams of code. in this way I appreciate the manual lift an LLM gives me.

New comment by blinkbat in "Ask HN: Is Agentic Coding really faster?"

blinkbat — Sun, 18 Oct 2026 22:27:25 +0000

I will never be able to type out a large feature at even 1/100th of the speed of today's frontier LLMs -- even if I literally had a complete plan of every line of syntax I'd use.

now, the correctness of said feature is still up for debate, but we cannot argue that the thing came into existence faster than human hands could have wrought.

New comment by blinkbat in "Show HN: Vibe coded a city builder set in ancient Rome"

blinkbat — Sun, 18 Oct 2026 22:26:29 +0000

panning is choppy, I would expect to be able to arrow or wasd pan as well.

New comment by blinkbat in "My Obituary for Programming"

blinkbat — Sun, 18 Oct 2026 22:20:55 +0000

I mean, if the AI can improve your program's speed by 2-3x, and you want people to use the program happily, you should probably run it past that AI at SOME point.

maybe it can teach you, if you do it methodically, how such speedups are possible for you to handmake in the future.

there's a real disconnect between "I liked making this" (which is great!) and "my users would be happier if this were faster". the users, sadly, do not care how much you liked writing the code if that code is their bottleneck.

New comment by blinkbat in "Ask HN: How are you all ensuring your AI code isn't slop?"

blinkbat — Sat, 17 Oct 2026 16:45:22 +0000

I do extremely regular audits

New comment by blinkbat in "AI companies plot "day after" scenarios for public revolt"

blinkbat — Sat, 10 Oct 2026 05:41:10 +0000

Yep seems like we could wrap that up in a day

New comment by blinkbat in "Need Unbiased and Real Assessment"

blinkbat — Sat, 10 Oct 2026 05:27:27 +0000

If you find it useful someone else might.